The paper introduces Replay-Selected Hindsight Distillation (RSHD), a method that transforms failed attempts in GRPO training into useful supervision. By having the policy write corrective notes for each failure and re-solving the problem with those notes, RSHD admits only those notes that lead to higher success rates than the original attempts. This approach enables learning from groups where all rollouts fail and improves performance across multiple model families and domains.
arXiv:2610.07898v1 Announce Type: new Abstract: Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt...
arXiv:2610.34951v1 Announce Type: cross Abstract: Recent methods for Reinforcement Learning with Verifiable Rewards (RLVR) use rollout diversity to improve reasoning performance or training efficienc...
arXiv:2607. 19313v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models.
ReDraft is a reference‑driven revision method for continual post‑training of large multimodal language models. It uses the model’s own incorrect outputs as references, revises them, verifies the revisions, and fine‑tunes on the accepted ones, thereby combining explicit supervision with policy proximity. On tasks such as Counting, Clock Reading, and Jigsaw, ReDraft outperforms standard supervised fine‑tuning and on‑policy methods, achieving higher target‑task gains while dramatically reducing forgetting.
arXiv:2607. 12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent.
arXiv:2609.35954v1 Announce Type: cross Abstract: Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience i...
The paper introduces Distill Until Divergence, a method for agentic reinforcement learning that uses error-truncated hindsight distillation. It routes two complementary hindsight skills—Positive for successful workflows and Negative for failure corrections—based on trajectory outcomes and error boundaries. The post-error segment is optimized solely by GRPO, preserving outcome-based learning while avoiding mismatched hindsight supervision.
arXiv:2610.20497v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual...
arXiv:2610.33667v1 Announce Type: new Abstract: Resolving a repository-level issue typically requires a software-engineering (SWE) agent to localize the faulty code, reproduce the failure, and patch...
arXiv:2608. 03674v1 Announce Type: new Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments.
arXiv:2605. 12652v2 Announce Type: replace-cross Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails.
arXiv:2608. 02011v2 Announce Type: replace Abstract: Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them.